arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2012.10035astro-ph.EPastro-ph.IMcs.LG
收藏

利用机器学习技术从BRITE数据中寻找可能的系外行星凌日

Searching for Possible Exoplanet Transits from BRITE Data through a Machine Learning Technique

National Tsing Hua University(国立清华大学)

Li-Chin Yeh, Ing-Guey Jiang

摘要:

通过机器学习技术检查了BRITE卫星的光度光变曲线,以调查是否有可能的系外行星围绕附近的明亮恒星移动。针对不同的过境时段,构建了几个卷积神经网络来搜索过境候选者。卷积神经网络的训练与BRITE光变曲线相结合的合成过境信号,直到准确率高于99.7 $\%$。我们的方法可以有效地导致少量可能的过境候选人。在这10个候选系统中,其中两个系统(HD 37465和HD 186882系统)在未来的观察中得到了更高优先级的随访。本研究中使用的卷积神经网络代码可在http://www.phys.nthu.edu.tw/ $\sim$ jiang/BRITE 2020 YehJiangCNN.tar.gz上公开获得。

英文摘要:

The photometric light curves of BRITE satellites were examined through a machine learning technique to investigate whether there are possible exoplanets moving around nearby bright stars. Focusing on different transit periods, several convolutional neural networks were constructed to search for transit candidates. The convolutional neural networks were trained with synthetic transit signals combined with BRITE light curves until the accuracy rate was higher than 99.7 $\%$. Our method could efficiently lead to a small number of possible transit candidates. Among these ten candidates, two of them, HD37465, and HD186882 systems, were followed up through future observations with a higher priority. The codes of convolutional neural networks employed in this study are publicly available at http://www.phys.nthu.edu.tw/$\sim$jiang/BRITE2020YehJiangCNN.tar.gz.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑